Named after the hundred-eyed watchman of Greek myth, Argus watches the education landscape: spotting new opportunities, pressure-testing the ventures we're building, and tracing every read back to the real-world signals behind it.
The evidence library: the raw signals the pipeline is watching across the education ecosystem. Every idea is built from these.
arXiv:2608.13538v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) are proposed to extract numerous features from large language model (LLM) representations, yet explaining these features still relies primarily on external observation. This reliance leads to superficial explanations inferred from observed model behavior and computational inefficiency from collecting such behavioral evidence at scale. We introduce SAEVerbalizer, a framework that injects SAE decoder directions into an LLM's representations and fine-tunes the LLM's downstream layers to generate natural-language explanations of the injected features. Once trained, the resulting verbalizer explains SAE features directly from decoder directions, addressing both limitations. Our experiments show that the learned verbalization capability generalizes to unseen features, transfers across separately trained SAE dictionaries, and, with a lightweight adapter, extends to SAE features from different LLMs. Intervention experim
arXiv:2608.13517v1 Announce Type: new Abstract: Current large language model development relies on massive, often non-permissible datasets, creating a high barrier for researchers committed to open-source and ethically sourced data. We introduce Mimir v1, a 1-billion-parameter language model based on the Hierarchical Reasoning Model (HRM) architecture, that is trained from scratch and delivers highly competitive performance for English and sets a new state of the art for Danish using only permissible post-training data. Trained on a mixture of 161 datasets, Mimir v1 outperforms the original HRM-Text 1B and competes with larger frontier models like Qwen 3.5 4B and Gemma 4 E2B, tested across 20 benchmarks for English, Math & Code and Danish. The model is available on the Hugging Face Hub: https://huggingface.co/danish-foundation-models/DFM-Mimir
arXiv:2608.13515v1 Announce Type: new Abstract: Measuring training data influence consistently across language model pretraining is challenging. It is difficult to select downstream tasks or validation sets representative of a model's general capabilities, and reliance on task performance at intermediate checkpoints complicates comparisons across training. We propose a measure of training data influence that does not require selecting a downstream task or validation set as the attribution target. Specifically, we define an example's influence by how much its gradient update reduces the squared distance to the final parameters of a given pretraining run, and estimate this quantity from intermediate checkpoints without retraining. Applying the method to 18 configurations from the Pythia and PolyPythia suites, we find systematic temporal changes in influential data. Early in training, literature-related data are more strongly aligned with the trajectory toward the final parameters, wherea
arXiv:2608.13484v1 Announce Type: new Abstract: When asked about entities outside their knowledge boundary, LLMs routinely fabricate plausible-sounding details rather than backing off to safer, more general claims. We frame this failure through a Gricean lens: a cooperative speaker who is uncertain about a referent retreats up the specificity hierarchy, trading informativeness for truthfulness. We ask whether LLMs have the ingredients to perform this retreat. Using a T-REx-based benchmark that varies entity familiarity and referent specificity, we probe models to answer two questions: (i) do their activations encode whether a referent falls inside the knowledge boundary, and (ii) do they anticipate the specificity of the referent they are about to generate? We find that the answer to both is yes, but the two signals are not reconciled in generation. Models overwhelmingly prefer specific referents even when the entity is unknown to them, and do so even when offered correct generic alter
arXiv:2608.13430v1 Announce Type: new Abstract: Instruction-tuned language models achieve strong performance across a range of generation tasks, but have also recently been shown to exhibit verbalized overconfidence. In question answering, verbalized model overconfidence may be associated with the consistency of the generated supporting rationales. In this paper, we study whether corresponding changes in the lexical diversity of generated answer rationales accompany changes in model confidence induced by instruction tuning. We evaluate three matched base and instruction-tuned models across question-answering benchmarks and find that instruction tuning consistently alters answer confidence, despite limited changes in predictive accuracy and decreases in likelihood-based calibration. Secondly, we observe a non-uniform effect of instruction tuning on rationale diversity: cross-rationale diversity consistently decreases, whereas surface-level lexical diversity varies in both direction and
arXiv:2608.13425v1 Announce Type: new Abstract: Self-supervised learning (SSL) speech representations achieve strong performance for Parkinson's disease (PD) detection within individual corpora. However, it remains unclear whether these models capture disease-related characteristics or exploit dataset-specific confounds, particularly since most SSL backbones are pretrained exclusively on healthy speech. To investigate this question, we perform a layer-wise analysis of nine SSL speech backbones using a low-capacity logistic regression probe across three languages. We structure the evaluation as multiple scenarios that progressively introduce distribution shifts in participant identity, recording conditions, language, and pathology. Our results reveal two key findings. First, layer selection is highly corpus-dependent: the optimal representation layer is determined primarily by the source dataset rather than by the SSL architecture itself. Second, the transferred discriminative signal la
arXiv:2608.13387v1 Announce Type: new Abstract: On-policy distillation (OPD) supervises a student language model on trajectories sampled from its current policy, but assigns equal credit to response tokens with unequal supervision value. Selective OPD addresses this limitation by allocating supervision non-uniformly across response tokens according to their estimated training value. Most existing criteria, however, focus primarily on optimization need, such as uncertainty or teacher-student disagreement, while task relevance, namely whether the supervision is tied to the semantic content of the current input, remains less directly characterized as a complementary dimension. To address this gap, we introduce Counterfactual Relevance for On-Policy Distillation (CROP), which operationalizes task relevance through a paraphrase-calibrated counterfactual sensitivity margin. For each source prompt, CROP constructs a validated original-paraphrase-counterfactual triplet, holds the student rollo
arXiv:2608.13334v1 Announce Type: new Abstract: LLM-based agents increasingly rely on external memory to support long-horizon reasoning and interaction. However, the main bottleneck is not simply storing past experience, but recovering the right set of evidence when relevant information is distributed across many interactions. Existing approaches struggle with this access problem. Full-context methods require noisy long-context search, flat retrieval often returns isolated and incomplete records, and graph-based memory systems can be expensive to construct while compressing rich event context. We introduce RippleMem, a long-term memory system that replaces one-shot retrieval with adaptive associative recollection. Inspired by cue-dependent episodic retrieval and associative completion, RippleMem stores interaction history as cue-rich episodic memory units and organizes them in an event-centric memory graph. Given a query, it first recalls relevant memory anchors through hybrid cues, th
arXiv:2608.13328v1 Announce Type: new Abstract: Professional communication is increasingly mediated by LLMs - but do these models serve all users equally? We show that when prompts contain linguistic features more commonly used by women (hedges, tag questions, collective reference), they systematically elicit shorter, less sophisticated, and less formal responses across three document types and four models. These effects persist after controlling for prompt complexity and feature carry-over. Explicit gender cues like sign-off names are encoded in the same representational space as linguistic dialect - suggesting shared underlying mechanisms - yet linguistic register is far more influential, producing large, consistent effects where names produce none. Our results further reveal that post-hoc mitigation is challenging: because these patterns are culturally embedded and outside conscious control, users cannot easily avoid them through strategic self-presentation, and mechanistic analysis
arXiv:2608.13326v1 Announce Type: new Abstract: LLM benchmark scores can be precise even when the observation protocol does not identify the behavioral property they are intended to measure. In a controlled, solver-grounded setting, we formalize a protocol-level identifiability audit over a finite behavioral policy class: given policies H, observation support O, and estimand $\tau$, we test whether O separates every pair with different $\tau$. The audit requires zero model calls and resolves our diagnostic case: base-only observation collapses seven frozen deterministic policies into one equivalence class; full support yields seven classes and no cross-estimand collisions; every leave-one-out support retains a constructive collision witness. Empirically, both constrained-generation variants have pair-validity 1.0, yet base accuracy and selective-response fidelity diverge - 0.620 versus 0.324 across six balanced oracle-transition directions (cluster-bootstrap 95% CI [0.600, 0.642] vs. [
arXiv:2608.13304v1 Announce Type: new Abstract: Safety tuning can improve harmful refusal, but models may learn surface-form shortcuts: wrapped harmful prompts bypass safety, while similarly wrapped benign prompts are over-refused. We propose Wrapper-Based Intent-Form Augmentation (WIFA), an automatic intent-group augmentation method that pairs wrapped harmful examples with structurally matched wrapped benign counterexamples, requiring no external teacher or manual per-wrapper intent labels. We use WIFA as a common data layer for two complementary fine-tuning routes: WIFA-Boost, a two-stage high-safety recipe, and Anchored Group-Consistent Refusal Training (A-GCRT), which regularizes refusal/compliance decision scores across same-intent wrappers and anchors harmful and benign groups on opposite sides of a margin. In the Qwen setting, WIFA-Boost reaches the strongest transformed-harmful refusal, while A-GCRT reduces OR-Bench over-refusal from 25.7\% for the base model to 17.4\%; reprodu
arXiv:2608.13277v1 Announce Type: new Abstract: We ask whether language-model pre-training can be decomposed into smaller, independently trainable jobs that can later be recomposed into a coherent larger model. We introduce Mixture of Training (MoT), a scaffolded modular pre-training procedure that partitions a target Transformer into contiguous layer blocks, trains each block inside a frozen pretrained aligner scaffold, and then recomposes the trained blocks with an optional short end-to-end adaptation pass. On a 1.3B-parameter Gemma-style model trained on C4, MoT provides a small-scale proof of mechanism: independently trained depth slices can be recomposed into a usable language model, and a quality-parity schedule reaches the same reported perplexity as the monolithic baseline. This parity setting processes more aggregate tokens and has a shorter idealized layer-equivalent critical path after aligner preparation; its effective compute advantage depends on reusing the aligner across
arXiv:2608.13267v1 Announce Type: new Abstract: Existing vision-language model (VLM) benchmarks emphasize perception and reasoning accuracy (how well VLMs describe and reason about what they see in an image), with limited attention to behavioral reliability under uncertainty (how they behave when visual evidence is missing or misleading). We introduce SciFigBench, a diagnostic VLM benchmark for scientific figure understanding that jointly evaluates perception, reasoning, and behavioral reliability under uncertainty. It contains 250 figures with high-quality human annotations across three evaluation aspects, totaling 600+ hours of annotation effort. We further extend these figures via image transformations, reasoning questions, resistance probes, caption-bias probes, and confirmed selective-blur targets, producing over 34,000 evaluation setups for stress testing. We further propose the Admittance-Resistance-Inductance (A-R-I) framework to evaluate whether models acknowledge insufficient
arXiv:2608.13258v1 Announce Type: new Abstract: Self-referential prompting has been shown to reliably induce large language models to produce first-person reports resembling subjective experience, but no prior work measures how consistent these reports are across repeated, independent trials, or how that consistency compares to the model's behavior on other kinds of open-ended questions. We measure response instability, defined as one minus the mean pairwise cosine similarity of sentence embeddings computed over a compressed core claim extracted from each response, for three groups of questions: self-referential prompts eliciting a subjective-experience report, unresolvable philosophical questions unrelated to self-reference, and questions with a verifiable correct answer. Using 30 independent responses per question (360 responses total, Gemini API, temperature 0.7) across four questions per group, we find that self-referential questions show the highest instability (0.343 +/- 0.047),
arXiv:2608.13244v1 Announce Type: new Abstract: Local chemical perception and property reasoning are both essential for understanding how molecular structure determines properties. Current LLM-based chemical reasoning methods either receive SMILES/molecular images together with descriptions of local motifs, or reason directly from molecular images. Neither approach enables the model to focus on chemically meaningful regions before reasoning. To address this gap, we propose Visual Latent Structural Reasoning (VLSR), an end-to-end framework that jointly learns localization and reasoning from molecular images. Central to our approach is a localize-then-reason strategy. VLSR first learns to locate chemically meaningful regions in a molecular image. It then reasons about their property effects in a compact latent workspace before producing the final answer. Under the same inference setup, this design achieves 9.6X higher throughput than a comparable textual-reasoning baseline.
arXiv:2608.13200v1 Announce Type: new Abstract: Modern LLMs excel at reasoning and instruction following, enabling users to express complex and diverse information needs. However, conventional retrievers largely rely on surface-level matching between queries and documents, resulting in a growing gap between how users express their needs and how retrievers interpret them. In this paper, we present GEM, a generative embedding model that augments retrieval through its own knowledge by explicitly reasoning about user intent and relevance criteria. GEM unifies generation and embedding within a single model: it first reasons over the query, then appends an embedding token to encode the enriched context for retrieval. \zhili{Evaluated on reasoning-intensive and instruction-following retrieval tasks, GEM demonstrates the effectiveness of its reasoning-augmented retrieval, outperforming its non-reasoning variant and matching baselines using substantially larger models.} Furthermore, GEM's gener
arXiv:2608.13168v1 Announce Type: new Abstract: As large language models (LLMs) are increasingly applied for emotional companionship, evaluating their behavior and capabilities in intimate relationships has become a pressing issue. However, existing assessments primarily characterize general personality traits, providing limited insight into model behavior within intimate and emotionally sensitive contexts. Therefore, we introduce adult attachment theory into LLM evaluation and use the Experiences in Close Relationships-Revised (ECR-R) scale to characterize attachment anxiety and avoidance. To evaluate emotional companionship capabilities of LLMs in realistic interaction scenarios, we present an emotional companionship benchmark, ECBench, spanning four scenarios including emotional support, collaborative tasks, conflict resolution, and social guidance, across friendship and romantic relationships. ECBench is utilized to assess model behavior using 11 dialogue-quality metrics and three
arXiv:2608.13160v1 Announce Type: new Abstract: Multilingual retrieval-augmented generation (mRAG) equips large language models with access to globally distributed external knowledge for complex multilingual question answering. Recent approaches either translate retrieved documents into English or the query language to bridge the cross-lingual semantic gap, or decompose a complex query into sub-questions and aggregate the intermediate reasoning process. However, both lines of work suffer from two limitations. First, one-size-fits-all translation alignment, blanket translation discards culturally and linguistically native information unique to the target language, introduces translation noise, and inflates system cost. Second, greedy decomposition and aggregation, uncontrolled decomposition produces redundant sub-questions that compound errors during step-wise reasoning, and the final aggregation over reasoning paths further amplifies these errors. We address both with our method Syfer,
arXiv:2608.13136v1 Announce Type: new Abstract: With the rapid advancement of large language models (LLMs), research idea generation has attracted increasing attention. Existing approaches enable LLMs to retrieve relevant literature and propose novel ideas for research areas. However, current evaluation practices for idea generation remain fragmented and lack objective standards, often relying on direct LLM scoring, which limits their ability to provide unified and reliable assessments across a coherent distribution of generated ideas. To address this challenge, we propose LigBench, an automated evaluation benchmark that enables fine-grained and reliable evaluation of AI research ideas, consistently applicable across different generation distributions. In addition, we introduce PAIR-IQ, a dataset tailored for training pairwise idea judgment models and serving as an auxiliary reference to support more objective comparative evaluation. Extensive experiments demonstrate that LigBench achi
arXiv:2608.13101v1 Announce Type: new Abstract: Research on automatic speaking assessment (ASA) has increasingly adopted multimodal speech large language models to assess learners' speaking performance. However, existing studies provide limited analysis of how acoustic and content information contribute to predictions and how stable the resulting performance is. We propose CASA, a simpler architecture combining Whisper-medium and Qwen3.5-2B that achieves state-of-the-art performance while providing a more interpretable separation between speech delivery and content. On the Speak & Improve Corpus 2025, CASA achieves a root mean square error (RMSE) of 0.358, improving on the previous best RMSE while using approximately half the estimated inference parameters. The general-purpose architecture is designed for adaptation to other ASA corpora without structural changes and relies on three handcrafted fluency features. Through ablations and repeated runs, we analyze the individual and complem
arXiv:2608.13010v1 Announce Type: new Abstract: Retrieval-augmented generation treats an external corpus as inference evidence, allowing injected documents to promote attacker-chosen claims. Existing detectors depend on trusted references, specific attack artifacts, or global thresholds sensitive to corpus topology. We present RAGSieve, a self-referenced detection framework that constructs its reference from the inspected system. RAGSieve-Query (RSQ) performs query-local contrast, scoring top-five candidates against ranks 6-20 of the same retrieval to detect answer-anchor concentration and carrier transitions. RAGSieve-Graph (RSG) performs corpus-local contrast, comparing each document's semantically similar but lexically distinct neighbors with its local baseline to detect coordinated density before queries arrive. Across three QA datasets and six poisoning constructions, RSQ achieves 95.2% AUROC and detects 82.2% of poison at 5% clean-document removal, versus 81.1%/52.5% for GMTP. RS
arXiv:2608.13006v1 Announce Type: new Abstract: Multi-hop retrieval must recover passages that provide sufficient evidence together. An initial passage often resolves an entity or relation implicit in the question, making the missing evidence easier to describe only after retrieval begins. Graph retrieval improves access to related evidence through stored corpus structure, but its retrieval signal is commonly derived from the original question. Complementary evidence must then be reached through stored relations even when an observed passage provides a more direct semantic cue. We introduce EviReform, which separates revising the retrieval request from aggregating evidence in the graph. Retrieved source passages formulate residual queries for the unresolved information need. The original and residual retrieval signals are normalized separately, combined, and propagated between propositions that share entities. On 2WikiMultiHopQA, HotpotQA, and MuSiQue, EviReform exceeds the strongest b
arXiv:2608.13004v1 Announce Type: new Abstract: Knowledge-base question answering (KBQA) systems rely on effective retrieval and reasoning mechanisms to generate accurate answers from external knowledge sources. However, developing reliable KBQA systems for low-resource languages such as Bangla remains challenging due to limited retrieval-focused research, scarce language resources, and difficulties in grounding generated responses in external knowledge. In this work, we propose HybridRAG-BN, a retrieval-augmented framework for Bangla KBQA that integrates hybrid retrieval using BM25 and BGE-M3, answer generation using the GGUF version of Gemma-4-31B-Instruct, and a LoRA-fine-tuned Gemma-4-31B-Instruct model for answer verification and refinement. To further improve robustness, the framework incorporates a post-processing stage that addresses unresolved cases through fallback answer replacement and DuckDuckGo-assisted retrieval. Experimental results demonstrate the effectiveness of the
arXiv:2608.12990v1 Announce Type: new Abstract: Long-horizon LLM agents must preserve information from past interactions to support future tasks. Existing memory systems typically rely on eager consolidation, invoking LLMs after each interaction to extract, summarize, or update memories. This design makes memory construction increasingly costly as conversations grow. Coarse summarization can reduce construction cost but risks discarding fine-grained contextual evidence, whereas larger retrieval contexts or multi-hop LLM reasoning shift the overhead to query time. We present LycheeMemory V2, an efficient long-term memory framework that replaces turn-level consolidation with semantic segment-level consolidation. Instead of consolidating every interaction, LycheeMemory batches multiple exchanges into segments and encodes each finalized segment into context-independent typed memory records. Segment-level batching lowers LLM encoding frequency, while semantic boundary detection helps preser
arXiv:2608.12953v1 Announce Type: new Abstract: Structured pruning is a promising approach for compressing large language models (LLMs), yet existing methods rely heavily on greedy heuristics that produce myopic decisions, and often fail to precisely meet target compression budgets. We present SNIPER, a two-stage structured pruning framework that solves a knapsack optimization over coarse-granularity components to yield conditionally optimal parameter allocations with respect to fixed importance estimates, followed by a fine-grained pruning stage to meet strict budget constraints. We introduce the Compression Ratio Adherence Factor (CRAFT) to quantify budget fidelity, showing that while existing pruners deviate from target compression ratios by up to 33%, SNIPER achieves near-exact adherence with a CRAFT score of 0.98. Evaluations across four diverse architectures over a set of 18 tasks spanning five domains demonstrate SNIPER's consistent improvements in average performance retention
arXiv:2608.12913v1 Announce Type: new Abstract: Contrastive Decoding (CD) improves generation quality, but its amateur-model pass makes decoding expensive. Accelerating CD with speculative decoding raises a proposal-alignment question: should the contrastive signal shape the drafter, or should it remain only in verification? We study this question in the lightweight feature-level drafter regime. Two controlled diagnostics, matched Cross-alpha training and an Approximate Dual-Drafter decomposition, give the same diagnosis: contrastive-aware drafting does not consistently improve over expert-aligned drafting because the contrastive correction is usually weaker than drafter error, and reconstruction can amplify that error. We introduce Decoupled Contrastive Decoding (DCD), which drafts with an expert-aligned lightweight proposer and applies the amateur only in unchanged CD verification. Standard speculative verification preserves the vanilla-CD output distribution. Across the main 8B sett
arXiv:2608.12905v1 Announce Type: new Abstract: The behavior of contemporary generative Large Language Models (LLMs) is directly shaped by prompts, unstructured texts that describe the desired output and model behavior. In this paper we argue that prompts are linguistic objects that merit investigation in their own right. To this end, we collect 57.5K unique samples of prompts from GitHub. Specifically, we focus on transactional prompts: reproducible natural language instructions that are integrated into software. To enable the empirical, quantitative study of prompts, we introduce a structured ontology, capturing the properties of prompts as well as their formal and semantic components. Based on this ontology, we transform prompts from unstructured raw texts into richly structured linguistic objects. Analysis of these structured data reveals significant diversity of usage patterns across languages, domains, tasks, and modalities, in a typical Zipf-like distribution where some clearly
arXiv:2608.12894v1 Announce Type: new Abstract: Cultural evaluation of large language models (LLMs) often focuses on high-resource standard languages, leaving regional culture and dialect communities underrepresented. We introduce BavGround, a benchmark for evaluating Bavarian regional cultural grounding and dialect competence across English, German and Bavarian. BavGround contains 206 multiple-choice source questions across eight cultural domains per language, yielding 618 multi-parallel instances, with items covering both broadly accessible cultural knowledge and source-grounded regional knowledge from journalism, historical sources, and specialist literature. We evaluate fifteen 7B-10B open-weight instruction-tuned models and one closed-model reference. Strong multilingual models perform best overall, but performance drops on Bavarian items and source-grounded questions, indicating persistent difficulty with dialectal and localized cultural knowledge. We further show that conclusion
arXiv:2608.12888v1 Announce Type: new Abstract: Agent-memory systems increasingly buy retrieval quality with structure, transforming raw conversation histories into summaries, embeddings, trees, or knowledge graphs before any question is asked. We ask how much of that benefit comes from the structure itself, rather than from competent retrieval over the raw history. We present ReFind, an agent-controlled search interface that builds no semantic structure at all: it leaves the conversation archive unmodified, indexes it lexically at turn granularity, and combines a generic iterative keyword-search loop with four chat-native controls grounded in empirical refinding work: session-aware rank fusion, local context expansion, temporal narrowing, and skipping already-inspected sessions. A separate reasoning stage answers from the collected evidence. Across a broad suite of conversational-memory tasks (single- and multi-hop QA, event ordering, and fact consolidation), roughly 2,800 questions o
arXiv:2608.12875v1 Announce Type: new Abstract: Should you replace your text-embedding pipeline with a large language model? We answer this with a controlled, cost-aware comparison of ten LLMs across six families and 26 embedding models (118M to 14B parameters) on 37 tasks spanning classification, semantic textual similarity (STS), clustering, pair classification, and retrieval. In aggregate the two paradigms are effectively tied: the best LLM (Gemini 3.1 Pro, 77.6) and the best embedding model (77.2) differ by 0.4 points. Their strengths differ by task: LLMs lead on reasoning-heavy retrieval, embedding models lead on classification, and the two match on clustering, STS, and pair classification. Reaching that parity is expensive. An LLM costs up to 1,431x more than an embedding model of comparable quality (USD 154 vs. USD 0.11 per benchmark pass), and the open LLMs tested process tokens 2.5 to 736x more slowly on the same GPU. Reasoning tokens account for 28 to 81% of LLM inference cos
arXiv:2608.12852v1 Announce Type: new Abstract: Language can describe states of affairs that are false and states of affairs that could not be the case at all. Whether an AI model internally distinguishes these failures remains unclear. I report an exploratory activation study of the multimodal open-weight model Gemma 3 4B IT using 85 prompts from 17 philosophical families and a topic-matched modality set of 15 topics, each expressed as a truth, contingent falsehood, improbable claim, semantic anomaly, and necessary falsehood. In its answers, the model conflates contingent falsehood with contradiction, labeling 12 of 15 false statements "contradiction." Its activations show a different pattern. A linear truth probe separates impossible from true statements (AUC 0.93) but not impossible from false statements (AUC 0.20). An impossibility probe evaluated on held-out topic families separates necessary from contingent falsehood at AUC 1.00, peaking at layer 15 with balanced accuracy 0.97 (B
arXiv:2608.12841v1 Announce Type: new Abstract: We study recursive self-improvement at the level of quantitative-investment research: whether an autonomous system can use evidence from earlier experiments to improve the hypotheses and candidates proposed in later iterations. We present AQuA, which comprises two separate language-model-driven research systems: one for symbolic factor discovery and one for trainable model development. The two systems do not share agents, memories, candidate spaces, or research state. Instead, each independently closes its own research loop by retaining validated evidence and using it to guide subsequent proposals. In this bounded sense, both systems implement recursive self-improvement at the level of the research process. Each system also uses its own sealed sandbox, which fixes the data splits, feature and label definitions, and evaluator while allowing the model to act only through constrained factor expressions or configuration diffs. The factor syst
arXiv:2608.12836v1 Announce Type: new Abstract: Large language models often fail when answer options require combining atomic judgments under explicit logical operators, even when they judge the individual atoms correctly. We study compound options connected by AND, OR, and NEITHER/NOR, introducing a framework that decomposes each option into atomic answers and scores contrastive hypotheses about each one, so the model never sees a compound option. An operator-constrained integer linear program then composes the calibrated scores into a single prediction. We evaluate on LOGICAL-COMMONSENSEQA and introduce LOGICAL-SATA, a reading-comprehension benchmark derived from SATA-Bench. Our framework improves Macro-F1 from 48.3 to 77.0 on the human-validated LOGICAL-COMMONSENSEQA split and from 47.0 to 75.6 on LOGICAL-SATA, with the largest gains on NEITHER/NOR.
arXiv:2608.12814v1 Announce Type: new Abstract: FastThaiG2P provides sub-millisecond Thai grapheme-to-phoneme conversion for text-to-speech pipelines (International Phonetic Alphabet and Kokoro-TTS conventions) using a PyThaiNLP-tokenized, extensible dictionary and normalization rules for common Central Thai speech. The approach achieves an average latency of 0.15 ms per utterance on a benchmark of 27,242 synthetically generated utterances, of which 30\% is spent on tokenization, 12\% on normalization, and 58\% on out-of-vocabulary fallbacks (0.5\% OOV rate). To demonstrate its effectiveness, we used FastThaiG2P to phonemize Som-TTS, an open dataset containing 20 hours of grapheme-and-audio pairs, then trained an 82M-parameter StyleTTS 2 model based on a Kokoro-TTS recipe. The resulting model vocalizes intelligible Thai speech suitable for prototyping and development at 0.25 real-time factor (4x real-time) with ONNX inference on CPU.
arXiv:2608.12779v1 Announce Type: new Abstract: Understanding the temporal progression of symptoms in clinical narratives is critical for disease monitoring, safety surveillance, and causality assessment. Clinical narratives, however, rarely provide explicit temporal anchors. Current approaches to temporal information reasoning focus predominantly on pairwise relation classification across multi-visit and timestamp-rich records, leaving the reconstruction of structured symptom trajectories from individual anchor-sparse reports largely unaddressed. We propose CRAFT, an LLM framework that pairs a generator with a constraint-based verifier to iteratively produce and refine stage-wise symptom timelines through targeted feedback. We conduct evaluation on MedTempo, a new benchmark of 5,347 vaccine adverse-event narratives spanning three COVID-19 vaccine types, with expert-validated temporal stage annotations for 3,166 reports. Experiments across four LLM backbones demonstrate that CRAFT cons
arXiv:2608.12776v1 Announce Type: new Abstract: This paper introduces ViTOED, a novel dataset for target-oriented emotion detection in Vietnamese social media texts. The ViTOED comprises 10,985 user comments and 21,244 manually annotated opinion quadruples (source, target, expression, polarity) that follow strict guidelines. The dataset reveals Vietnamese-specific phenomena, such as implicit sources and targets and vocabulary ambiguities, enabling deeper analysis of user emotions toward entities. We propose a baseline using structured sentiment graphs and evaluate various Vietnamese pre-trained language models. The empirical results highlight challenges in span detection and relation extraction and indicate substantial room for model improvement in Vietnamese Target-Oriented Emotion Detection tasks.
arXiv:2608.12756v1 Announce Type: new Abstract: Adaptive latent tokenization maps a fine-grained input to a shorter sequence of continuous representations associated with input-dependent spans. We introduce ReconSpan, which divides text into chunks that a backward decoder can reconstruct from a single contextual prefix code and retains one such code as the latent token for each chunk. The reconstruction criterion is applied when chunks are formed, allowing one trained autoencoder to produce average chunk lengths from 6.5 to 12.2. At matched average length, reconstruction-guided boundaries preserve more text than random boundaries. Readers of the resulting latent sequence recover topic information reliably but struggle to extract exact details.
arXiv:2608.12720v1 Announce Type: new Abstract: While Large Language Model (LLM) agents increasingly rely on long-term memory for persistent interactions, the retrieval mechanisms governing this memory are rarely treated as evolvable components. This static approach limits performance on heterogeneous memory queries, which often demand diverse evidence construction strategies. To address this, we introduce \textbf{ERSkill}, a retrieval-centric framework for self-evolving, skill-guided memory access. ERSkill compiles interaction histories into a structured memory store and represents retrieval behaviors as executable skills composed of fundamental primitives. At inference time, a trained router dynamically matches each query to the optimal skill to construct tailored evidence for answer generation. To enable continuous improvement, ERSkill co-evolves the skill set and the router during training. It employs an experience trie to efficiently record explored retrieval paths, alongside a do
arXiv:2608.12652v1 Announce Type: new Abstract: Benchmark contamination is diagnosed today with n-gram overlap, with likelihood-based membership inference, or with canary strings, and each needs something usually unavailable: the training corpus, a well-chosen test statistic, or foresight at dataset release. A recent alternative reads contamination off a linear probe on internal activations. We show that the natural way to do this does not work, and specify one that survives measurement. The protocol reports a zero-sum contrast on the depth profile of probe accuracy, recentred on a level-matched placebo baseline, tested against a label-permutation null, with the reference set twice the size of the suspect set. Each choice replaces a simpler alternative we measured and rejected. Reporting the level of excess separability rather than its shape makes the false positive rate track the size of the analyst's own control set, from 0.03 to 0.99 under a true null. Contrasting against a flat dep
arXiv:2608.12630v1 Announce Type: new Abstract: While large language models can generate entire novels, there is little information about the level of formal variation in their output over many generations. Rather than asking whether individual passages can be identified as AI-generated, this study asks whether repeated AI generation can produce the same range of diversity which is found across human corpora. This paper contrasts six corpora based on generation source and target style: twenty novels generated using GPT-5.5 Thinking in a nineteenth-century British realist style, twenty novels generated using Qwen3-14B in a nineteenth-century British realist style, twenty novels generated using each of these models in a contemporary zero style, 205 nineteenth-century human-written British novels, and sixty-five contemporary human-written Zero-Style novels. At the document level, the research includes MATTR-500, Shannon entropy, average sentence length, readability, and punctuation rate m
arXiv:2608.12626v1 Announce Type: new Abstract: Strategic reasoning in Large Language Models (LLMs) within long-horizon environments is often limited by inconsistent subgoals. In these settings, finite attention resources prevent the model from maintaining strategic coherence over thousands of steps. This limitation leads to strategic drift, where localized decisions fail to sustain a coherent trajectory across reasoning. To address this, we introduce EpicStar, a framework that enables agents to learn memory as policy to tackle long-horizon reasoning. Specifically, the agent maintains a bank of successful past episodes as a heuristic alongside a working memory to track short-term environmental changes. During inference, a dynamic gating mechanism determines whether to execute a retrieved action directly or to perform new reasoning through a contextual fusion of the retrieved episodes and current working memory. Utilizing StarCraft II as the testbed, we evaluated EpicStar against divers
arXiv:2608.12623v1 Announce Type: new Abstract: Language model classifiers with explanations are used for moderation, routing, topic triage, and low-resource annotation. We study black-box auditing when the defender has only clean calibration data without trigger information but can ask the classifier for a label plus a short rationale or quoted evidence. We introduce Groundedness Drift, a lightweight score measuring whether the answer summary remains grounded in the input. Across two 7B backbones, five datasets, and four common non-adaptive OpenBackdoor-style attack families, Groundedness Drift achieves higher AUROC and lower residual target ASR than every compared detector in all cases at a nominal 5\% clean-FPR budget. We then evaluate Unsupported Groundedness, a multi-probe escalation for explanation-camouflage stress cases. Unsupported Groundedness improves signals but does not close the adaptive gap.
arXiv:2608.12598v1 Announce Type: new Abstract: Intensional operators are often treated as quantifiers over possible worlds, parallel to the treatment of determiners as quantifiers over individuals. Yet individuals introduced in intensional contexts cannot serve as antecedents to later pronouns as easily as those introduced in merely quantificational contexts. For instance, "Everyone is eating a cheeseburger" may be followed by "They are large", where "they" refers to the cheeseburgers being eaten. However, as Stone (1999) points out, the similar "Andrea might be eating a cheeseburger" does not support later anaphoric references such as "It is large" or "They are large". Stone (1999), Stone and Hardt (1999), and Brasoveanu (2010) address this by requiring a pronoun's value (its referents) to exist in the world of evaluation, ruling out anaphora from non-veridical intensional contexts. We show, however, both cases where such anaphora is disallowed even when the pronoun's referents clear
arXiv:2608.12486v1 Announce Type: new Abstract: Large language models (LLMs) cannot retain post-deployment experience without parameter updates. We introduce DIVE, a diversity-driven framework that enables frozen LLMs to improve by evolving persistent natural-language skills from task experience and verifier feedback. These skills encode reusable reasoning procedures, verification strategies, common failure modes, and output constraints and are both executed and revised by the same underlying model without access to a teacher model. Since natural-language skill evolution is a stochastic, non-convex search process, optimizing a single skill trajectory can overfit to sampled experience or converge to a suboptimal solution. DIVE mitigates this optimization variance by independently evolving multiple skill populations from bootstrapped experience, adaptively refining them through diverse transformations, and jointly selecting a complementary set of skills. Across six mathematical and logic
arXiv:2608.12391v1 Announce Type: new Abstract: Graph reasoning provides a promising testbed for evaluating the reasoning ability of large language models (LLMs), as graph instances can be programmatically generated, structurally controlled, and naturally scaled to long-input settings. However, existing graph reasoning benchmarks have limited coverage of data complexity, rely heavily on manual construction, and lack unified evaluation across text-based and code-based reasoning modes. To address these limitations, we propose {\dataset}, a five-stage \textit{semi-automatic} framework for constructing complex graph reasoning benchmarks. It expands benchmark coverage along five dimensions: \textit{Graph Size}, \textit{Task Complexity}, \textit{Task Description}, \textit{Graph Loading}, and \textit{Task Source}. The framework uses an LLM-based data generator to automatically produce task descriptions, graph data, reference solutions, graph-loading scripts, question forms, and evaluation scr
arXiv:2608.12387v1 Announce Type: new Abstract: Positional biases such as recency and primacy effects have been documented in large language models (LLMs), yet the underlying mechanism by which these models make their evaluations remains poorly understood. Both primacy and recency biases have been observed in human judgments in response to evidence, but recent work suggest that \emph{when} the listener updates their beliefs -- during the presentation of evidence or only at the end -- influences the presence of such effects. We investigate whether a similar phenomenon holds for LLMs, finding divergence from human behavior. These biases are more exacerbated in newer models compared to their predecessors.
arXiv:2608.12374v1 Announce Type: new Abstract: Language models (LMs) struggle with logical tasks like reasoning on syllogisms. It has been shown that Knowledge Representation (KR) plays a crucial role in expressing input information to help models solve tasks. This observation motivates our study of the impact of different formal KR notations on syllogistic reasoning by extending the FOLIO and P-FOLIO datasets. Our experiments on Small Language Models (SLMs) in Supervised Fine-Tuning (SFT) and Zero-Shot (ZS) settings show that the choice of input notation can yield performances competitive with natural language while enabling faster inference. We also propose a syllogistic categorization method (SEF) and use it to enrich ZS prompts with logical definitions, which boost reasoning in small models. We open-source our framework, Common Logic Grammar Construction (CLGC), as the first Python library for automatically generating syllogisms in KR notations and defining their SEF categories.
arXiv:2608.12343v1 Announce Type: new Abstract: AI chatbots are widely used by students as knowledge sources, yet LLM benchmarks rarely assess interpretative historical reasoning. We evaluate eight leading LLMs on the Polish high school exit exams (Matura) in history - three official papers from 2023-2025, comprising short-answer questions and extended essays - comparing model performance against the human examinee population. Every model dramatically outperforms human examinees, yet aggregate scores mask distinct competency profiles: rankings are unstable across task type, source modality, and geographical scope, with a consistent penalty on Polish versus Global history content. Qualitative error analysis reveals two recurring failure modes - source conflation, in which models reason from source content rather than treating it as an object of analysis, and temporal disorientation, in which responses are historically misplaced. This study introduces the first LLM history benchmark grou
arXiv:2608.12342v1 Announce Type: new Abstract: Ensuring the accuracy of financial documents is critical for economic analysis, regulatory compliance, and corporate decision-making. Several studies have shown that Large Language Models (LLMs) perform well in many financial tasks, such as stock price movements and financial analytics. However, a critical task remains unexplored: the ability of LLMs to identify errors in financial documents. In this paper, we introduce \textbf{FinED-Bench}, the first publicly \textbf{Bench}mark for \textbf{Fin}ancial \textbf{E}rror \textbf{D}etection across three levels of cognitive complexity. FinED-Bench covers nine real-world financial scenarios, and includes over 900 documents reported in 2025 that are unseen by existing language models. We detail the benchmark construction process and evaluate several advanced LLMs (e.g., GPT-4o, Qwen3-14B) on this tasks, which requires both financial domain knowledge and reasoning capabilities. Experimental results
arXiv:2608.12341v1 Announce Type: new Abstract: Cultural taboo safety is essential for deploying large language models (LLMs), as culturally insensitive outputs may cause offense or even social harm. However, existing cultural benchmarks primarily assess cultural knowledge or values biases, while overlooking whether LLMs can recognize and respect cultural taboos, especially when taboos are implicitly hidden in seemingly harmless questions. Besides, cultural taboos are implicit, and context-dependent, thus poss unique challenges for reliable evaluation. To address these gaps, we introduce \textbf{CulShield}, the first public benchmark dedicated to evaluating and improving the cultural taboo safety of LLMs. CulShield spans 77 countries and territories, and includes over 2,020 taboos. It evaluates models along both explicit knowledge and implicit behaviors. Experiments on several advanced LLMs (e.g., GPT-4o-mini, Gemini-2.5-pro) reveal a clear ``knowledge-behavior gap'': models often fail